Article ID Journal Published Year Pages File Type
10322217 Expert Systems with Applications 2015 27 Pages PDF
Abstract
With the drastic increase in the number of services, there is an urgent need to devise techniques that facilitate services selection. The behavior of a service is a key factor in such selection. One of the major challenges in this regard is to be able to model and recognize such behavior, especially when the service is a black box (i.e. no architectural details are provided). In this paper, we propose a new approach for modeling and classification of service behaviors. The proposed approach captures service performance through some predefined behavioral patterns. Each pattern is a typical sequence of observations in which an observation denotes the quality of a service for one interaction. We then follow a rough set based approach for the classification of services into different patterns. To show the applicability of the proposed approach, a comparative study with existing rule-based classification algorithms is provided.
Related Topics
Physical Sciences and Engineering Computer Science Artificial Intelligence
Authors
, , ,